相关论文: SecReEvalBench: A Multi-turned Security Resilience…

As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, becomes critical to minimize risks. However, there is no…

Large language models are increasingly used for vulnerability detection, yet their reliability under different prompt formulations remains uncharacterized. We present PromptAudit, a controlled evaluation framework that isolates prompt…

Large language models (LLMs) are transforming everyday applications, yet deployment in cybersecurity lags due to a lack of high-quality, domain-specific models and training datasets. To address this gap, we present CyberPal 2.0, a family of…

Large language models (LLMs) have seen widespread applications across various domains, yet remain vulnerable to adversarial prompt injections. While most existing research on jailbreak attacks and hallucination phenomena has focused…

Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly vulnerable to jailbreak attacks that bypass safety alignment and induce harmful behaviors.…

Existing benchmarks for evaluating the security risks and capabilities (e.g., vulnerability detection) of code-generating large language models (LLMs) face several key limitations: (1) limited coverage of risk and capabilities; (2) reliance…

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…

Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary…

Multimodal Large Language Models (MLLMs) are showing strong safety concerns (e.g., generating harmful outputs for users), which motivates the development of safety evaluation benchmarks. However, we observe that existing safety benchmarks…

WalledEval is a comprehensive AI safety testing toolkit designed to evaluate large language models (LLMs). It accommodates a diverse range of models, including both open-weight and API-based ones, and features over 35 safety benchmarks…

Open-weight models provide researchers and developers with accessible foundations for diverse downstream applications. We tested the safety and security postures of eight open-weight large language models (LLMs) to identify vulnerabilities…

Despite impressive advances in large language models (LLMs), existing benchmarks often focus on single-turn or single-step tasks, failing to capture the kind of iterative reasoning required in real-world settings. To address this…

As large language models (LLMs) grow more powerful, ensuring their safety against misuse becomes crucial. While researchers have focused on developing robust defenses, no method has yet achieved complete invulnerability to attacks. We…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Large Language Models (LLMs) have training corpora containing large amounts of program code, greatly improving the model's code comprehension and generation capabilities. However, sound comprehensive research on detecting program…

Ensuring the safety of large language model (LLM) applications is essential for developing trustworthy artificial intelligence. Current LLM safety benchmarks have two limitations. First, they focus solely on either discriminative or…

Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security…

With the rapid popularity of large language models such as ChatGPT and GPT-4, a growing amount of attention is paid to their safety concerns. These models may generate insulting and discriminatory content, reflect incorrect social values,…

The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. In this paper, we observe that Multimodal Large Language Models…

Large Language Models (LLMs) like Codex are powerful tools for performing code completion and code generation tasks as they are trained on billions of lines of code from publicly available sources. Moreover, these models are capable of…